Оценка и вывод: от логитов к предсказанным меткам

import torch
import torch.nn.functional as F

# Example logits for 2-class problem (batch of 3)
logits = torch.tensor([[-1.2, 3.5], [2.1, -0.3], [0.4, 0.6]])
print('Logits:\n', logits)

# Convert to probabilities with softmax
probs = F.softmax(logits, dim=1)
print('Probabilities:\n', probs)
# Each row sums to 1
print('Row sums:', probs.sum(dim=1))

import torch
import torch.nn.functional as F
import numpy as np

logits = torch.tensor([1.0, 3.0, 0.5])  # 3 classes
probs = F.softmax(logits, dim=0)
print('Class probabilities:', probs.numpy().round(4))
# [0.0900, 0.6652, 0.2449] -- class 1 is most likely
print('Sum:', probs.sum().item())  # 1.0

# argmax gives the predicted class index
pred_class = torch.argmax(probs).item()
print('Predicted class:', pred_class)  # 1

import torch

# Logits from model output for a batch of 4 examples
logits = torch.tensor([
    [-2.1,  3.4],  # strongly positive
    [ 1.8, -0.5],  # negative
    [ 0.1,  0.2],  # uncertain, leans positive
    [-3.0, -1.0]   # both negative, less-negative wins
])

predictions = torch.argmax(logits, dim=1)
print('Predictions:', predictions.tolist())  # [1, 0, 1, 1]

labels = {'0': 'negative', '1': 'positive'}
for pred in predictions.tolist():
    print(labels[str(pred)])

import torch
from transformers import BertForSequenceClassification, BertTokenizer

# Assume model and tokenizer are already loaded and fine-tuned
id2label = {0: 'NEGATIVE', 1: 'POSITIVE'}

def predict(text, model, tokenizer, device):
    model.eval()
    inputs = tokenizer(text, return_tensors='pt',
                       truncation=True, max_length=256)
    inputs = {k: v.to(device) for k, v in inputs.items()}
    with torch.no_grad():
        logits = model(**inputs).logits
    pred_id = torch.argmax(logits, dim=1).item()
    return id2label[pred_id]

# result = predict('This film was absolutely wonderful!', model, tokenizer, device)
# print(result)  # POSITIVE

import torch
import torch.nn.functional as F

def predict_with_confidence(text, model, tokenizer, device):
    model.eval()
    id2label = {0: 'NEGATIVE', 1: 'POSITIVE'}
    inputs = tokenizer(text, return_tensors='pt',
                       truncation=True, max_length=256)
    inputs = {k: v.to(device) for k, v in inputs.items()}
    with torch.no_grad():
        logits = model(**inputs).logits
    probs = F.softmax(logits, dim=1).squeeze()
    pred_id = torch.argmax(probs).item()
    confidence = probs[pred_id].item()
    return id2label[pred_id], round(confidence, 4)

# label, conf = predict_with_confidence('Terrible movie.', model, tokenizer, device)
# print(label, conf)  # NEGATIVE 0.9732

from sklearn.metrics import classification_report, accuracy_score
import torch

all_preds, all_labels = [], []

model.eval()
with torch.no_grad():
    for batch in test_loader:
        outputs = model(
            input_ids=batch['input_ids'].to(device),
            attention_mask=batch['attention_mask'].to(device)
        )
        preds = torch.argmax(outputs.logits, dim=1).cpu().numpy()
        all_preds.extend(preds)
        all_labels.extend(batch['label'].numpy())

print('Accuracy:', accuracy_score(all_labels, all_preds))
print(classification_report(all_labels, all_preds,
      target_names=['NEGATIVE', 'POSITIVE']))

from sklearn.metrics import confusion_matrix
import seaborn as sns
import matplotlib.pyplot as plt
import numpy as np

cm = confusion_matrix(all_labels, all_preds)

plt.figure(figsize=(6, 5))
sns.heatmap(cm, annot=True, fmt='d', cmap='Blues',
            xticklabels=['NEG', 'POS'],
            yticklabels=['NEG', 'POS'])
plt.ylabel('True Label')
plt.xlabel('Predicted Label')
plt.title('BERT Confusion Matrix on IMDB Test Set')
plt.tight_layout()
plt.savefig('bert_confusion.png')

import torch
from torch.utils.data import DataLoader, TensorDataset
from transformers import BertTokenizer

def batch_predict(texts, model, tokenizer, device, batch_size=32):
    model.eval()
    all_predictions = []
    for i in range(0, len(texts), batch_size):
        batch_texts = texts[i:i+batch_size]
        enc = tokenizer(batch_texts, truncation=True, padding=True,
                        max_length=256, return_tensors='pt')
        enc = {k: v.to(device) for k, v in enc.items()}
        with torch.no_grad():
            logits = model(**enc).logits
        preds = torch.argmax(logits, dim=1).cpu().tolist()
        all_predictions.extend(preds)
    return all_predictions

import torch
import torch.nn.functional as F

# 5 classes, multi-label: a text can have multiple labels
logits = torch.tensor([[1.2, -0.5, 2.1, -1.8, 0.3]])
probs = torch.sigmoid(logits)
print('Per-class probabilities:', probs)

threshold = 0.5
predicted_labels = (probs > threshold).int()
print('Predicted labels (multi-hot):', predicted_labels)
# e.g., [1, 0, 1, 0, 0] -- classes 0 and 2 are predicted

import numpy as np

all_preds = np.array(all_preds)
all_labels = np.array(all_labels)
texts = test_dataset['text'] if hasattr(test_dataset, '__getitem__') else []

false_negatives = np.where((all_preds == 0) & (all_labels == 1))[0]
false_positives = np.where((all_preds == 1) & (all_labels == 0))[0]

print('False negatives (predicted NEG, true POS):')
for idx in false_negatives[:3]:
    print(' -', str(texts[idx])[:120] if texts else idx)

print('False positives (predicted POS, true NEG):')
for idx in false_positives[:3]:
    print(' -', str(texts[idx])[:120] if texts else idx)

import pandas as pd
import torch.nn.functional as F
import torch

results = []
id2label = {0: 'NEGATIVE', 1: 'POSITIVE'}

model.eval()
for i, text in enumerate(sample_texts):
    inputs = tokenizer(text, return_tensors='pt',
                       truncation=True, max_length=256)
    with torch.no_grad():
        logits = model(**inputs).logits
    probs = F.softmax(logits, dim=1).squeeze()
    pred = torch.argmax(probs).item()
    results.append({
        'text': text[:80],
        'true_label': id2label[sample_labels[i]],
        'predicted_label': id2label[pred],
        'confidence': round(probs[pred].item(), 4)
    })

df = pd.DataFrame(results)
df.to_csv('bert_predictions.csv', index=False)
print(df.head())